Update app.py

app.py

@@ -120,7 +120,7 @@ def fragment_single_abstract(abstract):
     conclusion = []
 
     embed_layer = EmbeddingLayer()
-    model = tf.keras.models.load_model("20k_5_epochs.keras", custom_objects={'EmbeddingLayer': embed_layer})
+    model = tf.keras.models.load_model("200k_10_epochs.keras", custom_objects={'EmbeddingLayer': embed_layer})
 
     data_by_character = split_sentences_by_characters(sentences)
     line_numbers = tf.one_hot(df["line_number"].to_numpy(), depth=15)
@@ -156,7 +156,7 @@ This app will take the abstract of a paper and break it down into five categorie
 The dataset used can be found in the [PubMed 200k RCT]("https://arxiv.org/pdf/1710.06071") and in [this repo](https://github.com/Franck-Dernoncourt/pubmed-rct). The model architecture
 was based off of ["Neural Networks for Joint Sentence Classification in Medical Paper Abstracts."](https://arxiv.org/pdf/1612.05251)
 
-This model achieved a testing accuracy of 88.12% and a F1 score of 87.92%. For the whole project, please visit [my GitHub](https://github.com/RyanTietjen/Paper-Fragmentation).
+This model achieved a testing accuracy of 88.2% and a F1 score of 88%. For the whole project, please visit [my GitHub](https://github.com/RyanTietjen/Paper-Fragmentation).
 
 How to use: